Mango Signal
Workforce Intelligence layer that detects engagement, performance, and operational risk across the workforce, recommends action to managers, drives close-the-loop change, and proves whether the organization improved.
MangoApps
Meet the agent
This app ships with a production AI agent — permission-aware, tenant-scoped, audit-logged, and governed by the Agent Development Lifecycle.
Mango Signal AI
Engagement health, risk segments, sentiment themes, action recommendations.
Overview
Mango Signal reads its signals straight out of the other MangoApps apps a business already runs — Surveys, Recognitions, Performance, Shift Feedback, News Feed, Ideas, and more — with no separate integration and no second login. A standalone listening tool has to be connected to each of those systems first; Mango Signal already sits inside them.
It blends the signals into one engagement health score for the company, a team, a location, a manager, or a segment, clusters the recurring themes behind that number, and flags which segments have dropped below the configured risk threshold. When a segment needs attention, it drafts a next action with AI — a person still decides whether to assign it. Completing the action posts a "you said, we did" update and starts measuring whether the score actually moved.
Individual employee feedback is never singled out — every score and theme stays aggregated to team, segment, or location.
Highlights
Capabilities
Cross-Signal Engagement Intelligence
-
Continuous 0..1 engagement health score for company, segment, team, location, or manager
-
Cross-app ingestion from Surveys, Recognitions, Performance, News Feed, and Shift Feedback
-
Weighted blend of sentiment, recognition, performance pulse, passive engagement, and themes
-
Nightly recompute with live on-demand fallback (no blank or stale dashboard)
-
Theme clustering with positive/negative polarity, signal counts, and average score
Risk Detection & Manager Alerts
-
Risk-segment detection, sorted worst-first, below a configurable threshold
-
Risk broken out across team, location, manager, and segment scopes
-
Automatic risk-alert emails to the scoped manager, deduplicated per manager
-
AI-recommended next actions per risk segment (Claude, with heuristic fallback)
Action & Close-the-Loop Workflow
-
Manager action items with assignee, due date, status, and linked source signals
-
Drawer-based create/edit without leaving the dashboard
-
AI-seeded action drafts prefilled from a risk segment
-
"You said, we did" close-the-loop update on completion — company-wide post plus contributor emails
-
News Feed vs Broadcast routing chosen by audience reach
Impact Measurement
-
Automatic pre-action baseline captured the moment an action is completed
-
Post-action re-measurement after a configurable window (default 30 days)
-
Per-action delta, delta %, and measured / positive / negative / inconclusive status
-
Impact rollup: measured, positive, negative, pending counts plus average delta
Analytics, Export & Import
-
Manager analytics: score, signal volume, risk segments, daily-volume trend
-
Selectable analysis windows (7 / 30 / 90 / 180 days)
-
Raw-signal export to CSV and XLSX (spreadsheet formula-injection safe)
-
CSV backfill import from a retired feedback tool, with a downloadable template
AI Assistant, Mobile & API
-
Mango Signal assistant in Ask AI (7 read tools + 2 write tools)
-
Every AI write (create or complete an action) requires explicit confirmation
-
Role-zoned surfaces: member dashboard, manager workflow, admin settings
-
Read-only mobile dashboard (score, top themes, my open actions)
-
Scoped REST API for mobile and external integrators (read & write)
-
Admin sample-data preview (one-click load and remove)
Limits & Specs
-
Engagement score scale: 0..1 (higher = healthier)
-
Score weighting: Sentiment 40% · Recognition 20% · Performance 15% · Engagement 15% · Themes 10%
-
Default score window: 30 days (admin-configurable 1–365)
-
Default risk threshold: 0.4 (admin-configurable 0.0–1.0)
-
Score recompute cadence: Nightly (~02:30 UTC) plus live on-demand
-
Impact re-measurement: Default 30 days after completion; needs ≥5 post-action signals
-
Risk-alert dedup: 7-day renotify / 90-day cutoff per manager
-
Apps feeding the score: 5 (Surveys, Recognitions, Performance, News Feed, Shift Feedback)
-
Pricing: License required (per-tenant opt-in, disabled by default)
Use cases
Resources
FAQ
Surveys collects feedback. Mango Signal sits on top of Surveys (and several other apps), interprets the cross-signal context, recommends an action, drives the change through an assign-and-complete workflow, and measures whether engagement actually improved. It reads Surveys data as one input — it does not replace it.
Mango IQ is competitive/market intelligence about external competitors — website crawling, content-gap and feature comparison, market themes. Mango Signal is workforce intelligence about your own employees — engagement, sentiment, themes, and risk across your people. Different subjects entirely; they share no data.
Five apps — Surveys, Recognitions, Performance, News Feed, and Shift Feedback — drive the weighted engagement score, theme clustering, and risk detection; Mango Signal works with whatever subset you have enabled. Time & Attendance, Leave Management, Ideas, and Ballots also ingest signals today (visible in the signal browse, export, and API) but don't yet factor into the score. You can also backfill history from a retired feedback tool via CSV import.
Mango Signal averages the last 30 days of normalized signals per type and blends them with fixed weights — sentiment 40%, recognition 20%, performance 15%, passive engagement 15%, and themes 10% — into a single 0..1 score. The window is admin-configurable (1–365 days), and scores are computed for the company and for every team, location, manager, and segment.
No. The dashboards, analytics, and AI assistant always aggregate to team, segment, or location scope; named individual sentiment is never surfaced. The one exception is the admin-only raw-signal browse/export used for backfill and BI, which is gated to administrators.
The close-the-loop flow fires: a baseline Impact row captures the current engagement score for the action's scope, a "you said, we did" update posts company-wide (News Feed for smaller scopes, Broadcast for large ones) while the contributors behind the action get a direct email, and a follow-up job re-measures the score after the configured window (default 30 days) to compute the delta.
When a manager-scoped segment drops below the risk threshold (default 0.4), that manager gets a deduplicated email alert. On the dashboard and in Ask AI, Mango Signal recommends one to three concrete next actions per risk segment — AI-drafted via Claude, with a stable heuristic fallback — which a manager can assign with an owner, due date, and linked signals.
The assistant is gated by the per-tenant agent setting. When enabled it appears in the Ask AI sidebar with seven read tools and two write tools (create action, update action status). Every write requires explicit confirmation before it persists, and manager-tier data stays gated to managers and admins even inside the agent.
Yes. Managers can export raw signals to CSV or XLSX (with a spreadsheet formula-injection guard) across 7/30/90/180-day windows, and there's a scoped read/write REST API under /api/v1/mango_signal for native mobile and external integrators, tenant-scoped and role-gated to match the web surface.
Mango Signal is a premium add-on that requires a license and is opt-in per tenant. It ships disabled by default until an administrator enables it from the Apps Marketplace. Contact your MangoApps administrator about turning it on for your organization.
